diff --git a/.DS_Store b/.DS_Store
index 3e28009..8d3c257 100644
Binary files a/.DS_Store and b/.DS_Store differ
diff --git a/NAMESPACE b/NAMESPACE
index c85ea04..ba3b738 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -1,6 +1,6 @@
 
 S3method(predict,usrData)
-S3method(predict,RecoS3)
+
 
 importFrom("recosystem", Reco, data_memory, out_file)
 
@@ -10,7 +10,6 @@ export(findYdotsMM,predict.ydotsMM,plot.ydotsMM,trainMM,
        formUserData,predict.usrData,cosDist,
        xvalMM,xvalMLE,xvalCos,
        plot.ydotsMM,plot.xvalb,
-       getTrainSet,getTestSet,trainReco,xvalReco,
        focusGrp,
        trainMultiplic,predict.MMmultiplic,xvalMultiplic,
        ratingness,covratingness)
diff --git a/R/.DS_Store b/R/.DS_Store
new file mode 100644
index 0000000..5008ddf
Binary files /dev/null and b/R/.DS_Store differ
diff --git a/R/.RData b/R/.RData
new file mode 100644
index 0000000..f0a6544
Binary files /dev/null and b/R/.RData differ
diff --git a/R/.Rhistory b/R/.Rhistory
index e69de29..d682e80 100644
--- a/R/.Rhistory
+++ b/R/.Rhistory
@@ -0,0 +1,224 @@
+# arguments:
+#   ratingsIn: input data, with first cols (userID,itemID,rating,
+#              covariates); data frame, unless cls is non-null, in which
+#              case this argument is the quoted name of the distributed
+#              data frame
+#   regressYdots; if TRUE, apply lm() to the estimated latent factors
+#                 (and their product), enabling rating prediction from the
+#                 resulting linear function of the factors; currently
+#                 only implemented if have no covariates
+#   cls: an R 'parallel' cluster
+# value:
+#   S3 class of type "ydots", with components:
+#      Y..: grand mean (0 if have covariates)
+#      Yi.: vector of mean ratings for each user
+#      Y.j: vector of mean ratings for each item
+#      regOjb: if have covariates, regression output, e.g. coefs
+findYdotsMM <- function(ratingsIn,regressYdots=FALSE,cls=NULL) {
+require(partools)
+if (is.null(cls)) {
+users = ratingsIn[,1]
+items = ratingsIn[,2]
+ratings = ratingsIn[,3]
+nms <- names(ratingsIn)
+haveCovs = ncol(ratingsIn) > 3
+if (haveCovs) {
+frml = as.formula(paste(nms[3],'~ .'))
+lmout = lm(frml,data=ratingsIn[,-(1:2)])
+fits = lmout$fitted.values
+ratings = ratings - fits
+Y.. = 0
+} else Y.. = mean(ratings)
+Yi. = tapply(ratings,users,mean) # means of all ratings per user
+Y.j = tapply(ratings,items,mean) # means of all ratings per item
+} else {
+stop('parallel version under construction')
+}
+ydots = list(grandMean=Y..,usrMeans=Yi.,itmMeans=Y.j)
+if (haveCovs) {
+ydots$regObj = lmout
+}
+if (regressYdots && !haveCovs) {
+yi. = Yi.[ratingsIn[,1]]
+y.j = Y.j[ratingsIn[,2]]
+# yij = yi. * y.j
+# ydots$regressYdots = coef(lm(ratings ~ yi. + y.j + yij))
+ydots$regressYdots = coef(lm(ratings ~ yi. + y.j))
+}
+class(ydots) = 'ydotsMM'
+invisible(ydots)
+}
+# alias
+trainMM <- findYdotsMM
+# check
+checkyd <- function() {
+check <-
+data.frame(userID = c(1,3,2,1,2),itemID = c(1,1,3,2,3),ratings=6:10)
+print(check)
+print(findYdotsMM(check))
+check$cv <- c(1,4,6,2,10)
+print(check)
+print(findYdotsMM(check))
+}
+# predict from output from coef(lm()); not used currently
+predict.lmcoef = function(coefs,testSet) {
+cbind(1,as.matrix(testSet)) %*% as.vector(coefs)
+}
+# predict() method for the 'ydots' class
+#
+# testSet in same form as ratingsIn in findYdots(), except that there
+# is no ratings column; regObj is as in the output of findYdots()
+#
+# returns vector of predicted values for testSet
+predict.ydotsMM = function(ydotsObj,testSet) {
+testSet$pred = ydotsObj$usrMeans[as.character(testSet[,1])] +
+ydotsObj$itmMeans[as.character(testSet[,2])] - ydotsObj$grandMean
+if (!is.null(ydotsObj$regObj))
+testSet$pred = testSet$pred + predict(ydotsObj$regObj,testSet[,-(1:2)])
+testSet$pred
+}
+# Wrapper for recosystem
+trainNM <- function(ratingsIn, trainprop = 0.5,cls = NULL,
+rnk = 10, recosystem = FALSE,regressYdots=FALSE){
+if(recosystem == TRUE){
+source((paste(system.file(package = 'rectools'),
+'recosys/xvalRecoParallel.R', sep = "")))
+res <- xvalReco(ratingsIn,trainprop,cls,rnk)
+}
+else {
+fullMatrix <- findYdotsMM(ratingsIn)
+require(NMF)
+library(NMF)
+res <- nmf(fullMatrix,10)
+}
+res
+}
+library(readr)
+ratingsIn <- read_csv("~/Desktop/RESEARCH/ratingsIn")
+View(ratingsIn)
+getwd()
+read.table("/Users/prajkuma/Desktop/RESEARCH/ratingsIn", sep ="")
+ratingsIn = read.table("/Users/prajkuma/Desktop/RESEARCH/ratingsIn", sep ="")
+ratingsIn = ratingsIn[,1:3]
+trainNM(ratingsIn)
+# Wrapper for recosystem
+trainNM <- function(ratingsIn, trainprop = 0.5,cls = NULL,
+rnk = 10, recosystem = FALSE,regressYdots=FALSE){
+if(recosystem == TRUE){
+source((paste(system.file(package = 'rectools'),
+'recosys/xvalRecoParallel.R', sep = "")))
+res <- xvalReco(ratingsIn,trainprop,cls,rnk)
+}
+else {
+fullMatrix <- findYdotsMM(ratingsIn)
+require(NMF)
+library(NMF)
+res <- nmf(as.matrix(fullMatrix),10)
+}
+res
+}
+trainNM(ratingsIn)
+fullMatrix <- findYdotsMM(ratingsIn)
+getTrainSet <- function(ratingsIn,trainprop = 0.5){
+rownew = nrow(ratingsIn)
+trainRow = floor(trainprop*rownew)
+trainidxs = sample(1:rownew,trainRow)
+trainSet = ratingsIn[trainidxs,]
+trainSet$trainidxs = trainidxs
+trainSet
+}
+### # returns the set-theoretic complement of the training set, to be used
+### # as the test set
+getTestSet <- function(ratingsIn, trainSet){
+testSet = ratingsIn[setdiff(1:nrow(ratingsIn),trainSet$trainidxs),]
+testSet
+}
+means <- findYdotsMM(ratingsIn)
+train <- getTrainSet(ratingsIn)
+test <- getTestSet(ratingsIn,train)
+preds <- predict.ydotsMM(means,test)
+means <- findYdotsMM(ratingsIn)
+ratingsIn = read.table("/Users/prajkuma/Desktop/RESEARCH/ratingsIn", sep ="", headers = TRUE)
+ratingsIn = read.table("/Users/prajkuma/Desktop/RESEARCH/ratingsIn", sep ="", header = TRUE)
+View(ratingsIn)
+ratingsIn = ratingsIn[,1:3]
+View(ratingsIn)
+means <- findYdotsMM(ratingsIn)
+buildMatrix <- function(ratingsIn,NAval=0){
+# deal with possible factors
+dmax <- function(d) {
+if (is.factor(d)) return(length(levels(d)))
+max(d)
+}
+users = ratingsIn[,1]
+movies = ratingsIn[,2]
+rating = ratingsIn[,3]
+newMatrix = matrix(NAval,
+nrow = dmax(users), ncol = dmax(movies))
+for(rows in 1:nrow(ratingsIn)){
+newMatrix[ratingsIn[rows,1],ratingsIn[rows,2]] = ratingsIn[rows,3]
+}
+return (newMatrix)
+}
+fullMatrix <- buildMatrix(ratingsIn)
+View(fullMatrix)
+means <- findYdotsMM(fullMatrix)
+# Wrapper for recosystem
+trainNM <- function(ratingsIn, trainprop = 0.5,cls = NULL,
+rnk = 10, recosystem = FALSE,regressYdots=FALSE){
+if(recosystem == TRUE){
+source((paste(system.file(package = 'rectools'),
+'recosys/xvalRecoParallel.R', sep = "")))
+res <- xvalReco(ratingsIn,trainprop,cls,rnk)
+}
+else {
+fullMatrix <- buildMatrix(ratingsIn)
+means <- findYdotsMM(ratingsIn)
+preds <- predict.ydotsMM(means,ratingsIn)
+require(NMF)
+library(NMF)
+res <- nmf(as.matrix(preds),10)
+}
+res
+}
+res <- trainNM(ratingsIn)
+# Wrapper for recosystem
+trainNM <- function(ratingsIn, trainprop = 0.5,cls = NULL,
+rnk = 10, recosystem = FALSE,regressYdots=FALSE){
+if(recosystem == TRUE){
+source((paste(system.file(package = 'rectools'),
+'recosys/xvalRecoParallel.R', sep = "")))
+res <- xvalReco(ratingsIn,trainprop,cls,rnk)
+}
+else {
+#fullMatrix <- buildMatrix(ratingsIn)
+means <- findYdotsMM(ratingsIn)
+preds <- predict.ydotsMM(means,ratingsIn)
+require(NMF)
+library(NMF)
+res <- nmf(as.matrix(preds),10)
+}
+res
+}
+res <- trainNM(ratingsIn)
+means <- findYdotsMM(ratingsIn)
+preds <- predict.ydotsMM(means,ratingsIn)
+head(preds)
+egg <- as.matrix(preds)
+View(egg)
+egg[,1] < 0
+res <- nmf(as.matrix(preds),10)
+egg[egg$V1 < 0, ]
+egg[egg < 0, ]
+egg[181,1]
+egg[181]
+egg[405]
+egg[egg(B<0)]
+egg[which(egg<0)]
+preds[which(preds<0)]=0
+res <- nmf(as.matrix(preds),10)
+preds[which(preds = NA)]=0
+preds[which(preds == NA)]=0
+res <- nmf(as.matrix(preds),10)
+is.na(preds)
+preds[which(is.na(preds) == TRUE)]
diff --git a/R/findYdotsMM.R b/R/findYdotsMM.R
index abe38f6..4181840 100644
--- a/R/findYdotsMM.R
+++ b/R/findYdotsMM.R
@@ -47,8 +47,6 @@ findYdotsMM <- function(ratingsIn,regressYdots=FALSE,cls=NULL) {
   if (regressYdots && !haveCovs) {
        yi. = Yi.[ratingsIn[,1]]
        y.j = Y.j[ratingsIn[,2]]
-       # yij = yi. * y.j
-       # ydots$regressYdots = coef(lm(ratings ~ yi. + y.j + yij))
        ydots$regressYdots = coef(lm(ratings ~ yi. + y.j))
   }
   
@@ -89,3 +87,53 @@ predict.ydotsMM = function(ydotsObj,testSet) {
    testSet$pred
 }
 
+buildMatrix <- function(ratingsIn,NAval=NA){
+  # deal with possible factors
+  dmax <- function(d) {
+    if (is.factor(d)) return(length(levels(d)))
+    max(d)
+  }
+  users = ratingsIn[,1]
+  movies = ratingsIn[,2]
+  rating = ratingsIn[,3]
+  newMatrix = matrix(NAval, 
+                     nrow = dmax(users), ncol = dmax(movies))
+  for(rows in 1:nrow(ratingsIn)){
+    newMatrix[ratingsIn[rows,1],ratingsIn[rows,2]] = ratingsIn[rows,3]
+  }
+  return (newMatrix)
+}
+
+# Wrapper for recosystem 
+
+trainNM <- function(ratingsIn, trainprop = 0.5,cls = NULL,
+                    rnk = 10, recosystem = FALSE,regressYdots=FALSE){
+  require(NMF)
+  library(NMF)
+  if(recosystem == TRUE){
+    source((paste(system.file(package = 'rectools'),
+                  'recosys/xvalRecoParallel.R', sep = "")))
+    res <- xvalReco(ratingsIn,trainprop,cls,rnk)
+  }
+  else {
+    fullMatrix <- buildMatrix(ratingsIn) # Matrix A (Step 1)
+    
+    approxMatrix <- findYdotsMM(ratingsIn) # Matrix V (Step 2)
+    
+    naMatrix <- as.data.frame(which(is.na(fullMatrix) == TRUE, arr.ind = TRUE))
+    naMatrix$ratings <- NA
+  
+     
+    preds <- predict.ydotsMM(approxMatrix,naMatrix) # Step 3
+  
+    
+    
+    fullMatrix[which(is.na(fullMatrix))] <- preds 
+    fullMatrix[fullMatrix < 0] <- 0
+    require(NMF)
+    res <- nmf(as.matrix(fullMatrix),10) # Step 4
+  }
+  res
+}
+
+
diff --git a/inst/.DS_Store b/inst/.DS_Store
index bb989f7..c0ef4ce 100644
Binary files a/inst/.DS_Store and b/inst/.DS_Store differ
diff --git a/inst/recosys/.DS_Store b/inst/recosys/.DS_Store
new file mode 100644
index 0000000..347d550
Binary files /dev/null and b/inst/recosys/.DS_Store differ
diff --git a/R/xvalRecoParallel.R b/inst/recosys/xvalRecoParallel.R
similarity index 100%
rename from R/xvalRecoParallel.R
rename to inst/recosys/xvalRecoParallel.R